No abstract

SUMMAR Y The aim of this study was to investigate two new scoring algorithms employing artificial neural networks and decision trees for distinguishing sleep and wake states in infants using actigraphy and to validate and compare the performance of the proposed algorithms with known actigraphy scoring algorithms. The study employed previously recorded longitudinal physiological infant data set from the Collaborative Home Infant Monitoring Evaluation (CHIME) study conducted between 1994 and 1998 [http:// dccwww.bumc.bu.edu/ChimeNisp/Main_Chime.asp; Sleep 26 (1997) 553] at five clinical sites around the USA. The original CHIME data set contains recordings of 1079 infants <1 year old. In our study, we used the overnight polysomnography scored data and ankle actimeter (Alice 3) raw data for 354 infants from this data set. The participants were heterogeneous and grouped into four categories: healthy term, preterm, siblings of SIDS and infants with apparent life-threatening events (apnea of infancy). The selection of the most discriminant actigraphy features was carried out using FisherÕs discriminant analysis. Approximately 80% of all the epochs were used to train the artificial neural network and decision tree models. The models were then validated on the remaining 20% of the epochs. The use of artificial neural networks and decision trees was able to capture potentially nonlinear classification characteristics, when compared to the previously reported linear combination methods and hence showed improved performance. The quality of sleep-wake scoring was further improved by including more wake epochs in the training phase and by employing rescoring rules to remove artifacts. The large size of the database (approximately 337 000 epochs for 354 patients) provided a solid basis for determining the efficacy of actigraphy in sleep scoring. The study also suggested that artificial neural networks and decision trees could be much more routinely utilized in the context of clinical sleep search.

No abstract

No abstract

No abstract

No abstract

No abstract

Computational modeling is now generally accepted as an essential procedure for the dynamic analysis of chemical processes. Many of these processes are distributed parameter systems, i.e., systems in which state variables depend on several independent variables (such as time and space) and which are described by sets of nonlinear partial differential equations (PDEs). The method of lines (MOL) is probably the most widely used approach to the solution of evolutionary PDEs, and the objective of this paper is to report on the development of a Matlab-based MOL toolbox. The toolbox contains a set of linear spatial approximation techniques, e.g., finite-difference methods, implemented using the concept of differentiation matrices, as well as a set of nonlinear spatial approximations, e.g., flux limiters. In addition, several time integrators, including basic explicit methods and some advanced linearly implicit methods, are included. The underlying philosophy of these developments is to provide the user with a variety of easily understood methods and a collection of application examples that can be used as Matlab templates for the rapid prototyping of new dynamic simulation codes. In this paper, Burgers' equation in one and two space dimensions, as well as a dynamic model of a three-zone tubular fixed-bed reactor used for studying benzene hydrogenation, and the poisoning kinetics of thiophene on a nickel catalyst are considered.